jikechao opened a new issue, #14614:
URL: https://github.com/apache/tvm/issues/14614

   For the following ONNX model, ONNXConverter will mistakenly parse the output 
number and thus triggered an assertion failure.
   
   ### The ONNX structure:
   
   
![image](https://user-images.githubusercontent.com/29506758/231821580-970f2abf-22cf-4aba-861f-0fc7ca4b033d.png)
   You can download the model by this link:  
https://github.com/jikechao/onnx_models/blob/main/model.onnx
   
   ### Crash message:
   ```
   Traceback (most recent call last):    
   ...
       irmod, params = relay.frontend.from_onnx(predict_model, shape_dict, 
freeze_params=True)
     File "/workplace/software/tvm/tvm/python/tvm/relay/frontend/onnx.py", line 
7346, in from_onnx
       mod, params = g.from_onnx(graph, opset)
     File "/workplace/software/tvm/tvm/python/tvm/relay/frontend/onnx.py", line 
6963, in from_onnx
       self._construct_nodes(graph)
     File "/workplace/software/tvm/tvm/python/tvm/relay/frontend/onnx.py", line 
7120, in _construct_nodes
       len(node_output), outputs_num, op_name
   AssertionError: Number of output mismatch 2 vs 1 in MaxPool.
   ```
   
   ### reproducible script:
   ```
   import onnx
   from tvm import relay
   
   onnx_model_path = "model.onnx"
   model = onnx.load(onnx_model_path)
   irmod, params = relay.frontend.from_onnx(model, {'x': (1, 1, 5, 5)}, 
freeze_params=True)
   ```
   
   
   
   
   


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to